Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements made by individuals, particularly in quotation format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a closing quotation mark and period

    np_acts-logits-general · gemini-2.0-flash

    periods and quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.82
     propOrder
    -0.70
     indígen
    -0.66
     ujednoznacz
    -0.65
     disambiguazione
    -0.64
    Попис
    -0.61
    ロウィン
    -0.61
    Дереккөздер
    -0.61
    RegressionTest
    -0.60
     queſta
    -0.59
    POSITIVE LOGITS
    findpost
    0.36
    MinWidth
    0.32
    Mayor
    0.32
     himself
    0.30
    UseVisualStyle
    0.30
    mui
    0.30
    WriteTagHelper
    0.29
    AndEndTag
    0.29
    /**
    0.29
    glUniform
    0.28
    Act Density 0.149%

    No Known Activations